Microsoft's Vibevoice, a long-form multi-speaker text-to-speech model available on Replicate, synthesizes conversational audio up to 90 minutes in a single pass with support for up to four distinct sp…
Xavriley and collaborators at CPJKU released Beat_this, a beat and downbeat tracking model from the ISMIR 2024 paper 'Beat This! Accurate Beat Tracking Without DBN Postprocessing'. The model detects p…
Qwen, Alibaba's AI team, has released Qwen-Image-2-Pro, a 20-billion-parameter text-to-image model now available on Replicate. The model excels at rendering complex text, particularly Chinese logograp…
Jichengdu at ByteDance developed Flux-Pulid, a face identity customization model built on the FLUX diffusion architecture that implements the PuLID method presented at NeurIPS 2024. The model uses con…
Elazarg's Nakdimon model, available on Replicate, is a character-level LSTM-based Hebrew diacritizer that restores diacritical marks to undiacritized Hebrew text without requiring dictionary resources…
Bria's Fibo-Edit model, available on Replicate, uses JSON-based control for deterministic, pixel-precise image editing, replacing ambiguous text prompts. The 8-billion-parameter model supports tasks l…
The Hypir-Sd2 model, developed by 0x3f3f3f3fun at the Shenzhen Institutes of Advanced Technology, performs image restoration and upscaling using diffusion-based score priors, built on Stable Diffusion…
Cwalo has released the All-In-One-Music-Structure-Analysis model on Replicate, a unified deep learning system that predicts tempo, beats, downbeats, segment boundaries, and labels from music audio, an…
Vufinder has released Vggt-1b-Depth, a feed-forward neural network based on research from Meta AI and the University of Oxford's Visual Geometry Group, which infers 3D scene attributes from single or …
Aaronjmars has released Unirig-Ai, an AI model on Replicate that automatically generates skeletal rigs and skinning weights for 3D models across humans, animals, and objects. Based on SIGGRAPH'25 UniR…
Kfarr's Sharp-Ml model, based on Apple's SHARP, converts a single photograph into 3D Gaussian splats in under a second via a neural network feedforward pass. The model achieves state-of-the-art result…
Adirik's Titanet-Large model on Replicate performs speaker identity verification by comparing two audio files and determining if they contain the same speaker. Built on NVIDIA's NeMo framework, the mo…
FoundationVision has released Infinity, a bitwise visual autoregressive text-to-image model that generates 1024×1024 photorealistic images in 0.8 seconds, outperforming diffusion models like SD3-Mediu…
Nateraw's Autotune model on Replicate performs pitch correction on voice audio, shifting vocal frequencies to target pitches using strategies like closest pitch or scale-based normalization. It is des…
Meta's 7.8 billion-parameter automatic speech recognition model, Meta-Omnilingual-Asr-7b, supports 1,693 languages with character error rates below 10% for 78% of covered languages. Built by Subformer…
Wan-Video's Wan-2.7-T2v, built on Alibaba's Wan 2.7 architecture, is an advanced text-to-video model that generates up to 15-second 1080p videos with synchronized audio. It uses a diffusion transforme…
A developer has completed a Google Summer of Code 2026 project for the sbi library, replacing its string-based network configuration with typed configuration objects across all estimator families. The…
A developer who built retrieval-augmented generation (RAG) and fine-tuning systems for clients compares the two approaches, scoring them on cost, latency, freshness, and failure modes. The comparison,…
A developer shipping a static Astro site to Cloudflare Pages discovered three platform defaults that silently broke the site on launch day. Cloudflare's managed robots.txt injected AI crawler blocks, …
Xingyao Byte, a developer-focused firm, argues that prompt injection cannot be solved at the prompt layer due to the architectural nature of LLMs, and instead advocates for system-level defenses such …